research
∙
04/20/2023
A User-Driven Framework for Regulating and Auditing Social Media
People form judgments and make decisions based on the information that t...
share
research
∙
03/24/2023
TRAK: Attributing Model Behavior at Scale
The goal of data attribution is to trace model predictions back to train...
research
∙
02/15/2023
Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
Distribution shifts are a major source of failure of deployed machine le...
research
∙
11/22/2022
ModelDiff: A Framework for Comparing Learning Algorithms
We study the problem of (learning) algorithm comparison, where the goal ...
research
∙
06/29/2022
Distilling Model Failures as Directions in Latent Space
Existing methods for isolating hard subpopulations and spurious correlat...
research
∙
02/01/2022
Datamodels: Predicting Predictions from Training Data
We present a conceptual framework, datamodeling, for analyzing the behav...
research
∙
12/31/2021
On Distinctive Properties of Universal Perturbations
We identify properties of universal adversarial perturbations (UAPs) tha...
research
∙
12/02/2021
Editing a classifier by rewriting its prediction rules
We present a methodology for modifying the behavior of a classifier by d...
research
∙
11/19/2021
Faster Sparse Minimum Cost Flow by Electrical Flow Localization
We give an O(m^3/2 - 1/762log (U+W)) time algorithm for minimum cost flo...
research
∙
10/15/2021
Combining Diverse Feature Priors
To improve model generalization, model designers often restrict the feat...
research
∙
05/11/2021
Leveraging Sparse Linear Layers for Debuggable Deep Networks
We show how fitting sparse linear models over learned deep feature repre...
research
∙
12/18/2020
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
As machine learning systems grow in scale, so do their training data req...
research
∙
08/11/2020
BREEDS: Benchmarks for Subpopulation Shift
We develop a methodology for assessing the robustness of models to subpo...
research
∙
06/17/2020
Noise or Signal: The Role of Image Backgrounds in Object Recognition
We assess the tendency of state-of-the-art object recognition models to ...
research
∙
05/25/2020
Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
We study the roots of algorithmic progress in deep policy gradient algor...
research
∙
05/22/2020
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Building rich machine learning datasets in a scalable manner often neces...
research
∙
05/19/2020
Identifying Statistical Bias in Dataset Replication
Dataset replication is a useful tool for assessing whether improvements ...
research
∙
03/10/2020
Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs
We present an m^11/8+o(1)log W-time algorithm for solving the minimum co...
research
∙
02/24/2020
The Two Regimes of Deep Network Training
Learning rate schedule has a major impact on the performance of deep lea...
research
∙
02/19/2020
On Adaptive Attacks to Adversarial Example Defenses
Adaptive attacks have (rightfully) become the de facto standard for eval...
research
∙
12/05/2019
Label-Consistent Backdoor Attacks
Deep neural networks have been demonstrated to be vulnerable to backdoor...
research
∙
06/06/2019
Image Synthesis with a Single (Robust) Classifier
We show that the basic classification framework alone can be used to tac...
research
∙
06/06/2019
Computer Vision with a Single (Robust) Classifier
We show that the basic classification framework alone can be used to tac...
research
∙
06/03/2019
Learning Perceptually-Aligned Representations via Adversarial Robustness
Many applications of machine learning require models that are human-alig...
research
∙
05/06/2019
Adversarial Examples Are Not Bugs, They Are Features
Adversarial examples have attracted significant attention in machine lea...
research
∙
02/18/2019
On Evaluating Adversarial Robustness
Correctly evaluating defenses against adversarial examples has proven to...
research
∙
11/06/2018
Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
We study how the behavior of deep policy gradient algorithms reflects th...
research
∙
11/01/2018
Spectral Signatures in Backdoor Attacks
A recent line of work has uncovered a new form of data poisoning: so-cal...
research
∙
09/09/2018
Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability
We explore the concept of co-design in the context of neural network ver...
research
∙
07/20/2018
Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
We introduce a framework that unifies the existing work on black-box adv...
research
∙
05/30/2018
There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)
We provide a new understanding of the fundamental nature of adversariall...
research
∙
05/29/2018
How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift)
Batch Normalization (BatchNorm) is a widely adopted technique that enabl...
research
∙
04/30/2018
Adversarially Robust Generalization Requires More Data
Machine learning models are often susceptible to adversarial perturbatio...
research
∙
12/21/2017
A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians
Sparsity-based methods are widely used in machine learning, statistics, ...
research
∙
12/07/2017
A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
Recent work has shown that neural network-based vision classifiers exhib...
research
∙
11/03/2017
k-server via multiscale entropic regularization
We present an O(( k)^2)-competitive randomized algorithm for the k-serve...
research
∙
11/02/2017
A Classification-Based Perspective on GAN Distributions
A fundamental, and still largely unanswered, question in the context of ...
research
∙
06/19/2017
Towards Deep Learning Models Resistant to Adversarial Attacks
Recent work has demonstrated that neural networks are vulnerable to adve...
research
∙
10/06/2011